Hybrid deep learning methods for phenotype prediction from clinical notes

TL;DR

This paper introduces a hybrid deep learning model combining BiLSTM or BiGRU with CNN layers, enhanced with pre-trained embeddings, to automatically extract patient phenotypes from clinical notes with improved accuracy.

Contribution

It presents a novel hybrid neural network architecture that improves phenotype extraction from clinical notes without relying on dictionaries or manual intervention.

Findings

The hybrid model outperforms existing models in phenotype identification accuracy.

Adding an extra CNN layer improves the F1-score.

BiGRU with FastText embeddings yields the best performance.

Abstract

Identifying patient cohorts from clinical notes in secondary electronic health records is a fundamental task in clinical information management. However, with the growing number of clinical notes, it becomes challenging to analyze the data manually for phenotype detection. Automatic extraction of clinical concepts would helps to identify the patient phenotypes correctly. This paper proposes a novel hybrid model for automatically extracting patient phenotypes using natural language processing and deep learning models to determine the patient phenotypes without dictionaries and human intervention. The model is based on a neural bidirectional sequence model (BiLSTM or BiGRU) and a CNN layer for phenotypes identification. An extra CNN layer is run parallel to the hybrid model to extract more features related to each phenotype. We used pre-trained embeddings such as FastText and Word2vec separately as the input layers to evaluate other embedding's performance. Experimental results using MIMIC III database in internal comparison demonstrate that the proposed model achieved significant performance improvement over existing models. The enhanced version of our model with an extra CNN layer obtained a relatively higher F1-score than the original hybrid model. We also showed that BiGRU layer with FastText embedding had better performance than BiLSTM layer to identify patient phenotypes.